An essential aspect of texture analysis is the extraction features that describe distribution values in local, spatial regions. We present a localized histogram layer for artificial neural networks. Instead computing global histograms as done previously, proposed directly computes and parameters are estimated during backpropagation. compare our method with state-of-the-art encoding methods such...

We introduce and study a Euclidean-invariant distance histogram function for curves. For a sufficiently regular plane curve, we prove that the cumulative distance histograms based on discretizing the curve by either uniformly spaced or randomly chosen sample points converge to our histogram function. Robustness of the curve histogram function under noise and pixelization of the curve is also es...

Color histogram is an important technique for color image database indexing and retrieving. In this paper, traditional color histogram is modified to capture spatial layout information of each color and three types spatial color histograms are introduced: annular, angular and hybrid color histograms. Experiments show that with a proper trade-off between the granularity in color dimensions and t...

We present a new segmentation algorithm based on probabilistic histograms and introduce certainty calculus and certainty color maps to solve the difficult problem of histogram separation. This new method is then compared to simple histogram and normalized histogram techniques. Using a set of experiments designed to measure the quality of segmentation, we have shown that certainty color maps is ...

This paper proposes creating new reversible marking technique. This originally based on indentifying parts of the image which are watermarked using two different Histogram Shifting (HS) modulations. One is Pixel Histogram shifting and other is Dynamic Prediction Error Histogram Shifting (DPEHS). This technique offers a very good compromise in terms of capacity and image quality preservation for...